© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 4-RES-JB
    11. 24134
    Prev
    Next
    INDEX
    Explanations

    statements or sentences punctuated with periods

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    timestamps in the format of military time

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 4-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.4.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    4
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Mechdragon
    -0.67
     quir
    -0.64
    ¾
    -0.64
     unbeat
    -0.63
     manufact
    -0.62
     transact
    -0.61
     behav
    -0.61
    ©¶æ
    -0.61
     glim
    -0.61
     administrator
    -0.61
    POSITIVE LOGITS
     EDT
    0.86
     Retrieved
    0.80
     Countdown
    0.74
    org
    0.73
     Madness
    0.71
     Boyle
    0.69
    Downloadha
    0.68
    endment
    0.68
     Afterwards
    0.67
    facebook
    0.67
    Activations Density 0.039%

    No Known Activations